# !pip install requests pandas matplotlib-venn folium geopandas seaborn statsmodels

import requests
import pandas as pd
import os
from matplotlib_venn import venn2
import matplotlib.pyplot as plt
import folium
from folium.plugins import MarkerCluster, FeatureGroupSubGroup
import geopandas as gpd
import seaborn as sns
import matplotlib.pyplot as plt
from statsmodels.tsa.stattools import adfuller
from statsmodels.tsa.arima.model import ARIMA
import warnings
warnings.filterwarnings('ignore')

def fetch_data(base_url, dataset, api_key, num_records=99, offset=0):
    all_records = []
    max_offset = 9900  # Maximum number of requests

    while True:
        # maximum limit check
        if offset > max_offset:
            break

        # Create API request URL
        filters = f'{dataset}/records?limit={num_records}&offset={offset}'
        url = f'{base_url}{filters}&api_key={api_key}'

        # Start request
        try:
            result = requests.get(url, timeout=10)
            result.raise_for_status()
            records = result.json().get('results')
        except requests.exceptions.RequestException as e:
            raise Exception(f"API request failed: {e}")
        if records is None:
            break
        all_records.extend(records)
        if len(records) < num_records:
            break

        # next cycle offset
        offset += num_records

    # DataFrame all data
    df = pd.DataFrame(all_records)
    return df

API_KEY = os.environ.get("API_KEY ")
# print("API Key:", API_KEY)
BASE_URL = 'https://data.melbourne.vic.gov.au/api/explore/v2.1/catalog/datasets/'

# data set name
PRE_COLONIAL_TREES = 'pre-colonial-plant-list'

pre_colonial_trees = fetch_data(BASE_URL, PRE_COLONIAL_TREES, API_KEY)

pre_colonial_trees

# data set name
CURRENT_TREES = 'trees-with-species-and-dimensions-urban-forest'

current_trees = fetch_data(BASE_URL, CURRENT_TREES, API_KEY)

current_trees

# Print available columns in the pre-colonial trees cleaned dataset
print("Available columns in pre-colonial trees dataset:")
print(pre_colonial_trees.columns.tolist())

# Print available columns in the current trees cleaned dataset
print("\nAvailable columns in current trees dataset:")
print(current_trees.columns.tolist())

Available columns in pre-colonial trees dataset:
['species', 'common_name_s', 'certain', 'beach_and_dunes', 'saltmarsh', 'coastal_marshlands_and_brackish_flats', 'swamp_scrub', 'woodlands_and_heathlands_on_sand', 'woodlands_and_forests_on_sedimentary_hills_valleys_and_ridges', 'grasslands_and_woodlands_on_fertile_plains', 'cliffs_and_escarpments', 'river_banks_and_creeklines', 'wet_heathland', 'freshwater_wetland', 'saltwater_wetland', 'most_likely_occurrence', 'epbc_category_of_threat', 'ffg_extinction_risk', 'ffg_category_of_threat']

Available columns in current trees dataset:
['com_id', 'common_name', 'scientific_name', 'genus', 'family', 'diameter_breast_height', 'year_planted', 'date_planted', 'age_description', 'useful_life_expectency', 'useful_life_expectency_value', 'precinct', 'located_in', 'uploaddate', 'coordinatelocation', 'latitude', 'longitude', 'easting', 'northing', 'geolocation']

# Columns to remove from the pre-colonial dataset
columns_to_remove_pre_colonial = ['epbc_category_of_threat', 'ffg_extinction_risk', 'ffg_category_of_threat', 'certain']

# Removing the specified columns from the pre-colonial trees dataset
pre_colonial_trees_cleaned = pre_colonial_trees.drop(columns=columns_to_remove_pre_colonial)

# Print available columns in the pre-colonial trees cleaned dataset after removal
print("Available columns in pre-colonial trees dataset after removal:")
print(pre_colonial_trees_cleaned.columns.tolist())

# Columns to remove from the current trees dataset
columns_to_remove_current = ['age_description', 'useful_life_expectency', 'useful_life_expectency_value', 'precinct', 'diameter_breast_height', 'coordinatelocation', 'easting', 'northing', 'geolocation']

# Removing the specified columns from the current trees dataset
current_trees_cleaned = current_trees.drop(columns=columns_to_remove_current)

# Print available columns in the current trees cleaned dataset after removal
print("\nAvailable columns in current trees dataset after removal:")
print(current_trees_cleaned.columns.tolist())

Available columns in pre-colonial trees dataset after removal:
['species', 'common_name_s', 'beach_and_dunes', 'saltmarsh', 'coastal_marshlands_and_brackish_flats', 'swamp_scrub', 'woodlands_and_heathlands_on_sand', 'woodlands_and_forests_on_sedimentary_hills_valleys_and_ridges', 'grasslands_and_woodlands_on_fertile_plains', 'cliffs_and_escarpments', 'river_banks_and_creeklines', 'wet_heathland', 'freshwater_wetland', 'saltwater_wetland', 'most_likely_occurrence']

Available columns in current trees dataset after removal:
['com_id', 'common_name', 'scientific_name', 'genus', 'family', 'year_planted', 'date_planted', 'located_in', 'uploaddate', 'latitude', 'longitude']

# Print available columns in the pre-colonial trees cleaned dataset
print("Available columns in pre-colonial trees dataset:")
print(pre_colonial_trees_cleaned.columns.tolist())

# Print available columns in the current trees cleaned dataset
print("\nAvailable columns in current trees dataset:")
print(current_trees_cleaned.columns.tolist())

Available columns in pre-colonial trees dataset:
['species', 'common_name_s', 'beach_and_dunes', 'saltmarsh', 'coastal_marshlands_and_brackish_flats', 'swamp_scrub', 'woodlands_and_heathlands_on_sand', 'woodlands_and_forests_on_sedimentary_hills_valleys_and_ridges', 'grasslands_and_woodlands_on_fertile_plains', 'cliffs_and_escarpments', 'river_banks_and_creeklines', 'wet_heathland', 'freshwater_wetland', 'saltwater_wetland', 'most_likely_occurrence']

Available columns in current trees dataset:
['com_id', 'common_name', 'scientific_name', 'genus', 'family', 'year_planted', 'date_planted', 'located_in', 'uploaddate', 'latitude', 'longitude']

# Rename "Scientific Name" column to "Species" in the current trees dataset
current_trees_renamed = current_trees_cleaned.rename(columns={"scientific_name": "species"})

# Verify the column renaming by printing the columns of the updated DataFrame
print("Available columns in current trees dataset after renaming:")
print(current_trees_renamed.columns.tolist())

Available columns in current trees dataset after renaming:
['com_id', 'common_name', 'species', 'genus', 'family', 'year_planted', 'date_planted', 'located_in', 'uploaddate', 'latitude', 'longitude']

current_trees_renamed

# Extracting species lists from both datasets
pre_colonial_species = set(pre_colonial_trees_cleaned['species'].unique())
current_species = set(current_trees_renamed['species'].unique())

# Creating the Venn diagram
plt.figure(figsize=(10, 7))
venn2([pre_colonial_species, current_species], ('Pre-Colonial Trees', 'Current Trees'))
plt.title('Comparison of Tree Species Diversity: Pre-Colonial vs Current')
plt.show()

# Extract species sets
pre_colonial_species = set(pre_colonial_trees_cleaned['species'].unique())
current_species = set(current_trees_renamed['species'].unique())

# Determine shared and unique species
shared_species = pre_colonial_species.intersection(current_species)
lost_species = pre_colonial_species.difference(current_species)
gained_species = current_species.difference(pre_colonial_species)

# Print results
print(f"Shared Species: {len(shared_species)}")
print(f"Lost Species: {len(lost_species)}")
print(f"Gained Species: {len(gained_species)}")

Shared Species: 16
Lost Species: 1051
Gained Species: 327

# Convert DataFrame to GeoDataFrame
gdf = gpd.GeoDataFrame(
    current_trees_renamed,
    geometry=gpd.points_from_xy(current_trees_renamed.longitude, current_trees_renamed.latitude),
    crs="EPSG:4326"
)

# Initialize a map centered around Melbourne
melbourne_map = folium.Map(location=[-37.8136, 144.9631], zoom_start=12)

# Use MarkerCluster to manage multiple markers
marker_cluster = MarkerCluster().add_to(melbourne_map)

# Create FeatureGroupSubGroups for parks and streets within the MarkerCluster
park_group = FeatureGroupSubGroup(marker_cluster, 'Parks')
street_group = FeatureGroupSubGroup(marker_cluster, 'Streets')
park_group.add_to(melbourne_map)
street_group.add_to(melbourne_map)

# Add markers to the appropriate subgroup based on their location
for idx, row in gdf.iterrows():
    marker = folium.CircleMarker(
        location=[row.geometry.y, row.geometry.x],
        radius=3,
        color='green' if row['located_in'] == 'Park' else 'red',
        fill=True,
        fill_color='green' if row['located_in'] == 'Park' else 'red',
        popup=f"Species: {row['species']}, Planted: {row['date_planted']}"
    )
    if row['located_in'] == 'Park':
        marker.add_to(park_group)
    else:
        marker.add_to(street_group)

# Add LayerControl to toggle parks and streets
folium.LayerControl().add_to(melbourne_map)

# Display the map
melbourne_map

# Ensure the 'year_planted' column is treated as integers
current_trees_renamed['year_planted'] = pd.to_numeric(current_trees_renamed['year_planted'], errors='coerce')

# Filtering out any rows where 'year_planted' might be zero or invalid
current_trees_filtered = current_trees_renamed[current_trees_renamed['year_planted'] > 0]

# Create the plot
plt.figure(figsize=(15, 8))
ax = sns.countplot(x='year_planted', data=current_trees_filtered, palette='viridis')
plt.xticks(rotation=90)
plt.title('Number of Trees Planted Per Year')
plt.ylabel('Number of Trees')
plt.xlabel('Year Planted')

# Adding counts above the bars
for p in ax.patches:
    ax.annotate(f'{int(p.get_height())}', (p.get_x() + p.get_width() / 2., p.get_height()),
                ha='center', va='center', fontsize=10, color='black', xytext=(0, 5),
                textcoords='offset points')

plt.tight_layout()
plt.show()

# Summing up habitat data
habitat_data = pre_colonial_trees_cleaned.drop(columns=['species', 'common_name_s', 'most_likely_occurrence'])
habitat_totals = habitat_data.sum().sort_values(ascending=False)

# Plotting habitat data
plt.figure(figsize=(12, 8))  # Adjusted figure size for better fit
habitat_totals = habitat_data.sum().sort_values(ascending=False)
ax = habitat_totals.plot(kind='bar', color='teal')
plt.title('Pre-Colonial Tree Species Habitat Distribution')
plt.ylabel('Number of Species Associations')
plt.xlabel('Habitat Type')
plt.xticks(rotation=45, ha='right')  # Adjust label alignment and rotation
plt.tight_layout()  # Adjust layout to make room for label text

# Adding text annotations at the top of each bar
for p in ax.patches:
    ax.annotate(f'{int(p.get_height())}', (p.get_x() + p.get_width() / 2., p.get_height()), 
                ha='center', va='bottom', color='black', xytext=(0, 5), textcoords='offset points')

plt.show()

# Separate trees into parks and streets
trees_in_parks = current_trees_renamed[current_trees_renamed['located_in'] == 'Park']
trees_in_streets = current_trees_renamed[current_trees_renamed['located_in'] == 'Street']

# Calculate total number of trees in parks and streets
total_parks_trees = trees_in_parks.shape[0]
total_streets_trees = trees_in_streets.shape[0]

# Focus on common names and species for simplicity
parks_info = trees_in_parks[['common_name', 'species']].value_counts().reset_index(name='count')
streets_info = trees_in_streets[['common_name', 'species']].value_counts().reset_index(name='count')

# Choose how many top entries to display
top_entries = 10  # Change this to 20 if you prefer

# Visualization of Species Distribution with Counts
plt.figure(figsize=(14, 7))

# Trees in Parks
plt.subplot(1, 2, 1)
ax1 = sns.barplot(x='count', y='common_name', data=parks_info.head(top_entries), palette='Greens_d')
plt.title(f'Top {top_entries} Trees in Parks (Total: {total_parks_trees})')
plt.xlabel('Number of Trees')
plt.ylabel('Common Name')
# Add counts above the bars
for p in ax1.patches:
    ax1.annotate(f'{int(p.get_width())}', (p.get_x() + p.get_width(), p.get_y() + p.get_height() / 2),
                 ha='left', va='center', xytext=(5, 0), textcoords='offset points')

# Trees in Streets
plt.subplot(1, 2, 2)
ax2 = sns.barplot(x='count', y='common_name', data=streets_info.head(top_entries), palette='Blues_d')
plt.title(f'Top {top_entries} Trees in Streets (Total: {total_streets_trees})')
plt.xlabel('Number of Trees')
plt.ylabel('Common Name')
# Add counts above the bars
for p in ax2.patches:
    ax2.annotate(f'{int(p.get_width())}', (p.get_x() + p.get_width(), p.get_y() + p.get_height() / 2),
                 ha='left', va='center', xytext=(5, 0), textcoords='offset points')

plt.tight_layout()
plt.show()

# Print the lists of top trees in parks and streets
print(f"Trees in Parks - Top {top_entries}: (Total Trees: {total_parks_trees})")
print(parks_info.head(top_entries).to_string(index=False))

print(f"\nTrees in Streets - Top {top_entries}: (Total Trees: {total_streets_trees})")
print(streets_info.head(top_entries).to_string(index=False))

Trees in Parks - Top 10: (Total Trees: 6083)
     common_name                    species  count
   River red gum   Eucalyptus camaldulensis    896
      Yellow Box      Eucalyptus melliodora    371
 Drooping sheoak Allocasuarina verticillata    342
    Black Wattle            Acacia mearnsii    206
    River Sheoak   Casuarina cunninghamiana    197
Lightwood Wattle             Acacia implexa    174
     English Elm              Ulmus procera    173
     Spotted Gum          Corymbia maculata    159
      Yellow Gum      Eucalyptus leucoxylon    154
    Black Wattle         Acacia melanoxylon    135

Trees in Streets - Top 10: (Total Trees: 3916)
        common_name                  species  count
       London Plane    Platanus x acerifolia    602
        Spotted Gum        Corymbia maculata    231
Smooth-barked apple        Angophora costata    151
                Elm            Ulmus unknown    150
        English Elm            Ulmus procera    104
    Chinaberry Tree          Melia azedarach    102
      River red gum Eucalyptus camaldulensis     95
            Pin Oak        Quercus palustris     93
   Japanese Zelkova          Zelkova serrata     92
          Brush Box    Lophostemon confertus     92

# Set of species in the pre-colonial dataset
pre_colonial_species_set = set(pre_colonial_trees_cleaned['species'])

# Set of species in the current dataset
current_species_set = set(current_trees_renamed['species'])

# Find species that are lost (present in pre-colonial but not in current)
lost_species_set = pre_colonial_species_set.difference(current_species_set)

# Filter the pre-colonial dataset to get the common names of these lost species
lost_species_details = pre_colonial_trees_cleaned[pre_colonial_trees_cleaned['species'].isin(lost_species_set)][['species', 'common_name_s']]

# Print the lost species and their common names
print("Lost Species and Their Common Names:")
print(lost_species_details)

Lost Species and Their Common Names:
                                    species  \
0          Acacia mucronata var. longifolia   
2     Acacia verticillata var. verticillata   
3                           Acaena echinata   
4                      Acrotriche prostrata   
5                      Acrotriche serrulata   
...                                     ...   
1062        Xanthorrhoea minor subsp. lutea   
1063                 Xerochrysum bracteatum   
1064     Zostera muelleri subsp. capricorni   
1065       Zostera muelleri subsp. muelleri   
1066               Zygophyllum billardierei   

                                   common_name_s  
0     Narrow-leaf Wattle, Variable Sallow Wattle  
2                                  Prickly Moses  
3                                   Sheep's Burr  
4                          Trailing Ground-Berry  
5                                     Honey Pots  
...                                          ...  
1062                Small Grass Tree, Toolimerin  
1063            Golden Everlasting, Straw Flower  
1064                                   Eel-grass  
1065                           Dwarf Grass-wrack  
1066                              Coast Twinleaf  

[1051 rows x 2 columns]

# Print the shape of each dataset
print("Shape of Current Trees Renamed Dataset:", current_trees_renamed.shape)
print("Shape of Pre-Colonial Trees Cleaned Dataset:", pre_colonial_trees_cleaned.shape)

Shape of Current Trees Renamed Dataset: (9999, 11)
Shape of Pre-Colonial Trees Cleaned Dataset: (1067, 15)

# Print all column names in the DataFrame to verify the correct name of the year_planted column
print(current_trees_renamed.columns)

Index(['com_id', 'common_name', 'species', 'genus', 'family', 'year_planted',
       'date_planted', 'located_in', 'uploaddate', 'latitude', 'longitude'],
      dtype='object')

# Make sure 'year' is a datetime object and extract the year if it's not just the year number
current_trees_renamed['year_planted'] = pd.to_datetime(current_trees_renamed['year_planted'], format='%Y').dt.year

# Aggregate data by year to get the total count of trees planted each year
yearly_data = current_trees_renamed.groupby('year_planted').size().reset_index(name='Tree_Count')
yearly_data.set_index('year_planted', inplace=True)  # Set the year as the index, ensuring it is a datetime index for time series modeling
yearly_data.index = pd.to_datetime(yearly_data.index, format='%Y')

yearly_data['Tree_Count'].plot(title='Annual Tree Plantings')
plt.ylabel('Number of Trees Planted')
plt.show()

result = adfuller(yearly_data['Tree_Count'])
print('ADF Statistic:', result[0])
print('p-value:', result[1])

# Interpret the p-value
if result[1] < 0.05:
    print("Data is stationary")
else:
    print("Data is not stationary, differencing might be needed")

ADF Statistic: -3.7409619938582823
p-value: 0.0035725200943580787
Data is stationary

# Fitting the ARIMA model (parameters should be optimized based on your specific dataset)
model = ARIMA(yearly_data['Tree_Count'], order=(1,1,1))  # Example parameters
model_fit = model.fit()

# Model summary
print(model_fit.summary())

                               SARIMAX Results                                
==============================================================================
Dep. Variable:             Tree_Count   No. Observations:                   23
Model:                 ARIMA(1, 1, 1)   Log Likelihood                -159.939
Date:                Mon, 06 May 2024   AIC                            325.879
Time:                        20:44:57   BIC                            329.152
Sample:                             0   HQIC                           326.650
                                 - 23                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1          0.2862      0.194      1.474      0.140      -0.094       0.667
ma.L1         -0.9994      0.271     -3.695      0.000      -1.530      -0.469
sigma2      1.076e+05   2.52e-06   4.27e+10      0.000    1.08e+05    1.08e+05
===================================================================================
Ljung-Box (L1) (Q):                   0.06   Jarque-Bera (JB):                 2.76
Prob(Q):                              0.81   Prob(JB):                         0.25
Heteroskedasticity (H):               0.02   Skew:                             0.83
Prob(H) (two-sided):                  0.00   Kurtosis:                         3.53
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.21e+26. Standard errors may be unstable.

# Example forecasts from the ARIMA model
forecast_values = model_fit.forecast(steps=5)

# Convert forecasted values to integers (rounded)
forecast_values_rounded = [int(round(value)) for value in forecast_values]

# Create a DataFrame to display the forecast with corresponding years
forecast_years = range(2022, 2027)  # Adjust the range based on your specific needs
forecast_df = pd.DataFrame({
    'Year': forecast_years,
    'Forecasted Plantings': forecast_values_rounded
})

# Print the DataFrame to see the formatted output
print(forecast_df.to_string(index=False))

 Year  Forecasted Plantings
 2022                   422
 2023                   424
 2024                   425
 2025                   425
 2026                   425

# Splitting data into train and test sets
train = yearly_data['Tree_Count'][:-5]
test = yearly_data['Tree_Count'][-5:]

# Fit model on train data
model = ARIMA(train, order=(1,1,1))
model_fit = model.fit()

# Forecast
forecasts = model_fit.forecast(steps=5)

# Visualization of the forecast alongside actual data
plt.figure(figsize=(12,6))
plt.plot(yearly_data['Tree_Count'], label='Original')
plt.plot(pd.date_range(start=test.index[0], periods=5, freq='A'), forecasts, label='Forecasts', color='red')
plt.legend()
plt.show()

# Calculate accuracy metrics
from sklearn.metrics import mean_squared_error, mean_absolute_error

mae = mean_absolute_error(test, forecasts)
rmse = mean_squared_error(test, forecasts, squared=False)
print('MAE:', mae)
print('RMSE:', rmse)

MAE: 45.423455778613665
RMSE: 54.30332134806747

	com_id	common_name	scientific_name	genus	family	diameter_breast_height	year_planted	date_planted	age_description	useful_life_expectency	useful_life_expectency_value	precinct	located_in	uploaddate	coordinatelocation	latitude	longitude	easting	northing	geolocation
0	1546404	River Sheoak	Casuarina cunninghamiana	Casuarina	Casuarinaceae	NaN	2013	2013-01-07	None	None	NaN	None	Park	2021-01-10	{'lon': 144.97177997020128, 'lat': -37.8180699...	-37.818070	144.971780	321479.34	5812432.31	{'lon': 144.97177997020128, 'lat': -37.8180699...
1	1038666	Claret Ash	Fraxinus angustifolia subsp. oxycarpa	Fraxinus	Oleaceae	26.0	1998	1998-11-09	Semi-Mature	11-20 years	20.0	None	Park	2021-01-10	{'lon': 144.96069216093832, 'lat': -37.7815772...	-37.781577	144.960692	320414.93	5816460.51	{'lon': 144.96069216093832, 'lat': -37.7815772...
2	1439845	Kanooka	Tristaniopsis laurina	Tristaniopsis	Myrtaceae	NaN	2009	2009-09-08	None	None	NaN	None	Street	2021-01-10	{'lon': 144.9455194257097, 'lat': -37.79259845...	-37.792598	144.945519	319105.53	5815208.27	{'lon': 144.9455194257097, 'lat': -37.79259845...
3	1070962	Spotted Gum	Corymbia maculata	Corymbia	Myrtaceae	17.0	2007	2007-06-14	Semi-Mature	31-60 years	60.0	None	Street	2021-01-10	{'lon': 144.9421772126995, 'lat': -37.78013819...	-37.780138	144.942177	318780.78	5816584.46	{'lon': 144.9421772126995, 'lat': -37.78013819...
4	1066252	River red gum	Eucalyptus camaldulensis	Eucalyptus	Myrtaceae	19.0	2006	2006-02-20	Semi-Mature	61+ years	80.0	None	Street	2021-01-10	{'lon': 144.92039340703647, 'lat': -37.7905765...	-37.790577	144.920393	316887.98	5815383.70	{'lon': 144.92039340703647, 'lat': -37.7905765...
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9994	1066718	Yellow Box	Eucalyptus melliodora	Eucalyptus	Myrtaceae	NaN	2006	2006-09-14	None	None	NaN	None	Park	2021-01-10	{'lon': 144.9546546149572, 'lat': -37.78488602...	-37.784886	144.954655	319891.23	5816081.73	{'lon': 144.9546546149572, 'lat': -37.78488602...
9995	1735402	Manuka	Kunzea ericoides	Kunzea	Myrtaceae	NaN	2018	2018-05-30	None	None	NaN	None	Park	2021-01-10	{'lon': 144.9514066985289, 'lat': -37.79316880...	-37.793169	144.951407	319625.34	5815156.36	{'lon': 144.9514066985289, 'lat': -37.79316880...
9996	1656707	Norfolk Island Pine	Araucaria heterophylla	Araucaria	Araucariaceae	NaN	2017	2017-04-26	None	None	NaN	None	Street	2021-01-10	{'lon': 144.9471755893213, 'lat': -37.81988993...	-37.819890	144.947176	319317.91	5812183.04	{'lon': 144.9471755893213, 'lat': -37.81988993...
9997	1604462	Lightwood Wattle	Acacia implexa	Acacia	Fabaceae	NaN	2015	2015-08-25	None	None	NaN	None	Park	2021-01-10	{'lon': 144.9524311587096, 'lat': -37.79529060...	-37.795291	144.952431	319720.71	5814922.89	{'lon': 144.9524311587096, 'lat': -37.79529060...
9998	1049080	River red gum	Eucalyptus camaldulensis	Eucalyptus	Myrtaceae	NaN	1998	1998-12-16	None	None	NaN	None	Park	2021-01-10	{'lon': 144.94552257177912, 'lat': -37.7903449...	-37.790345	144.945523	319100.31	5815458.34	{'lon': 144.94552257177912, 'lat': -37.7903449...

	com_id	common_name	species	genus	family	year_planted	date_planted	located_in	uploaddate	latitude	longitude
0	1546404	River Sheoak	Casuarina cunninghamiana	Casuarina	Casuarinaceae	2013	2013-01-07	Park	2021-01-10	-37.818070	144.971780
1	1038666	Claret Ash	Fraxinus angustifolia subsp. oxycarpa	Fraxinus	Oleaceae	1998	1998-11-09	Park	2021-01-10	-37.781577	144.960692
2	1439845	Kanooka	Tristaniopsis laurina	Tristaniopsis	Myrtaceae	2009	2009-09-08	Street	2021-01-10	-37.792598	144.945519
3	1070962	Spotted Gum	Corymbia maculata	Corymbia	Myrtaceae	2007	2007-06-14	Street	2021-01-10	-37.780138	144.942177
4	1066252	River red gum	Eucalyptus camaldulensis	Eucalyptus	Myrtaceae	2006	2006-02-20	Street	2021-01-10	-37.790577	144.920393
...	...	...	...	...	...	...	...	...	...	...	...
9994	1066718	Yellow Box	Eucalyptus melliodora	Eucalyptus	Myrtaceae	2006	2006-09-14	Park	2021-01-10	-37.784886	144.954655
9995	1735402	Manuka	Kunzea ericoides	Kunzea	Myrtaceae	2018	2018-05-30	Park	2021-01-10	-37.793169	144.951407
9996	1656707	Norfolk Island Pine	Araucaria heterophylla	Araucaria	Araucariaceae	2017	2017-04-26	Street	2021-01-10	-37.819890	144.947176
9997	1604462	Lightwood Wattle	Acacia implexa	Acacia	Fabaceae	2015	2015-08-25	Park	2021-01-10	-37.795291	144.952431
9998	1049080	River red gum	Eucalyptus camaldulensis	Eucalyptus	Myrtaceae	1998	1998-12-16	Park	2021-01-10	-37.790345	144.945523

	species	common_name_s	certain	beach_and_dunes	saltmarsh	coastal_marshlands_and_brackish_flats	swamp_scrub	woodlands_and_heathlands_on_sand	woodlands_and_forests_on_sedimentary_hills_valleys_and_ridges	grasslands_and_woodlands_on_fertile_plains	cliffs_and_escarpments	river_banks_and_creeklines	wet_heathland	freshwater_wetland	saltwater_wetland	most_likely_occurrence	epbc_category_of_threat	ffg_extinction_risk	ffg_category_of_threat
0	Acacia mucronata var. longifolia	Narrow-leaf Wattle, Variable Sallow Wattle	NaN	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0	1.0	None	None	None
1	Acacia pycnantha	Golden Wattle	1.0	0.0	0.0	0.0	1.0	2.1	3.2	3.1	2.1	2.1	0.0	0.0	0	3.2	None	None	None
2	Acacia verticillata var. verticillata	Prickly Moses	NaN	0.0	0.0	0.0	3.1	3.1	0.0	0.0	0.0	3.1	1.0	0.0	0	3.1	None	None	None
3	Acaena echinata	Sheep's Burr	1.0	0.0	0.0	0.0	0.0	1.0	3.1	3.1	3.1	2.1	0.0	0.0	0	3.1	None	None	None
4	Acrotriche prostrata	Trailing Ground-Berry	NaN	0.0	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0	1.0	None	None	None
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1062	Xanthorrhoea minor subsp. lutea	Small Grass Tree, Toolimerin	NaN	0.0	0.0	0.0	0.0	2.1	1.0	0.0	0.0	0.0	0.0	0.0	0	2.1	None	None	None
1063	Xerochrysum bracteatum	Golden Everlasting, Straw Flower	NaN	0.0	0.0	0.0	0.0	1.0	0.0	0.0	0.0	0.0	0.0	0.0	0	1.0	None	None	None
1064	Zostera muelleri subsp. capricorni	Eel-grass	NaN	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	3	3.2	None	None	None
1065	Zostera muelleri subsp. muelleri	Dwarf Grass-wrack	NaN	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	2	2.2	None	None	None
1066	Zygophyllum billardierei	Coast Twinleaf	NaN	2.1	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0	2.1	None	None	None

Tree History

Scenario

Skills Demonstrated in the Tree Mapping Project

1. Geospatial Analysis

2. Data Visualization

3. Programming and Technology

4. Critical Thinking and Problem Solving

5. Communication and Presentation

Project Goal: Melbourne Tree Species Analysis for Conservation Effort

Key Activities

Expected Outcome

Impact

Datasets

Installing all necessasory packages (optional)¶

Importing all the necessory libraries¶

Importing datasets¶

Preprocess the Data¶

Displaying Available Columns¶

Removing unwanted columns¶

Printing Available Columns after Removing Unwanted Columns¶

Renaming Columns to Match Datasets¶

Analysis & Visualization¶

1. Historical vs. Current Species Diversity (Venn Diagram)¶

Historical vs. Current Species Diversity (Venn Diagram)¶

2. Change in Species Abundance Over Time¶

Change in Species Abundance Over Time¶

3. Geographical Distribution of Trees (Map Visualization)¶

Geographical Distribution of Trees (Map Visualization)¶

4. Time-Series Analysis of Tree Planting¶

Time-Series Analysis of Tree Planting¶

5. Habitat Analysis for Pre-Colonial Species¶

Habitat Analysis for Pre-Colonial Species¶

6. Ecological Dynamics of Tree Species in Parks vs. Streets in Melbourne¶

Ecological Dynamics of Tree Species in Parks vs. Streets in Melbourne¶

Key Observations¶

Comparison¶

Identify Lost Species¶

Identifying Lost Tree Species¶

Dataset Dimensions Overview¶

Timeseries Model Fitting (ARIMA Model Forecasting)¶

Step 1: Data Preparation¶

Step 2: Visualize the Data¶

Timeseries Model Fitting (ARIMA Model Forecasting)¶

Step 1: Data Preparation¶

Step 2: Visualize the Data¶

Step 3: Check for Stationarity¶

Check for Stationarity¶

Stationarity Testing¶

Step 4: Fit the ARIMA Model¶

Fit the ARIMA Model¶

Model Fitting¶

Step 5: Forecast Future Plantings¶

Forecast Future Plantings¶

Generating Forecasts¶

Step 6: Model Validation¶

Advanced ARIMA Model Implementation and Evaluation¶

Model Training and Forecasting¶

Visualization¶

Accuracy Metrics¶

Goodness of Fit¶

Summary¶

Comprehensive Conclusion of Urban Forestry Analysis¶

Overview of Analysis¶

Key Findings and Insights¶

Forecasted Tree Planting Needs¶

Challenges and Rting precision.¶

Policy and Planning Recommendations¶

Concluding Thoughts¶

References¶